SEARCH · Search NASA

Results for “Image navigation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 451 records · Page 25

All sources NASA NTRS DOE OSTI

NASA NTRS1995

Algorithms for detection of objects in image sequences captured from an airborne imaging system

This research was initiated as a part of the effort at the NASA Ames Research Center to design a computer vision based system that can enhance the safety of navigation by aiding the pilots in detecting various obstacles on the runway during critical section of the flight such as a landing maneuver. The primary goal is the development of algorithms for detection of moving objects from a sequence of images obtained from an on-board video camera. Image regions corresponding to the independently moving objects are segmented from the background by applying constraint filtering on the optical flow computed from the initial few frames of the sequence. These detected regions are tracked over subsequent frames using a model based tracking algorithm. Position and velocity of the moving objects in the world coordinate is estimated using an extended Kalman filter. The algorithms are tested using the NASA line image sequence with six static trucks and a simulated moving truck and experimental results are described. Various limitations of the currently implemented version of the above algorithm are identified and possible solutions to build a practical working system are investigated.

Kasturi, Rangachar↗

NASA NTRS2009

Wrap-Around Out-the-Window Sensor Fusion System

The Advanced Cockpit Evaluation System (ACES) includes communication, computing, and display subsystems, mounted in a van, that synthesize out-the-window views to approximate the views of the outside world as it would be seen from the cockpit of a crewed spacecraft, aircraft, or remote control of a ground vehicle or UAV (unmanned aerial vehicle). The system includes five flat-panel display units arranged approximately in a semicircle around an operator, like cockpit windows. The scene displayed on each panel represents the view through the corresponding cockpit window. Each display unit is driven by a personal computer equipped with a video-capture card that accepts live input from any of a variety of sensors (typically, visible and/or infrared video cameras). Software running in the computers blends the live video images with synthetic images that could be generated, for example, from heads-up-display outputs, waypoints, corridors, or from satellite photographs of the same geographic region. Data from a Global Positioning System receiver and an inertial navigation system aboard the remote vehicle are used by the ACES software to keep the synthetic and live views in registration. If the live image were to fail, the synthetic scenes could still be displayed to maintain situational awareness.

Fox, Jeffrey↗

NASA NTRS2003

Design, Development and Testing of the Miniature Autonomous Extravehicular Robotic Camera (Mini AERCam) Guidance, Navigation and Control System

Engineers at NASA Johnson Space Center have designed, developed, and tested a nanosatellite-class free-flyer intended for future external inspection and remote viewing of human spaceflight activities. The technology demonstration system, known as the Miniature Autonomous Extravehicular Robotic Camera (Mini AERCam), has been integrated into the approximate form and function of a flight system. The primary focus has been to develop a system capable of providing external views of the International Space Station. The Mini AERCam system is spherical-shaped and less than eight inches in diameter. It has a full suite of guidance, navigation, and control hardware and software, and is equipped with two digital video cameras and a high resolution still image camera. The vehicle is designed for either remotely piloted operations or supervised autonomous operations. Tests have been performed in both a six degree-of-freedom closed-loop orbital simulation and on an air-bearing table. The Mini AERCam system can also be used as a test platform for evaluating algorithms and relative navigation for autonomous proximity operations and docking around the Space Shuttle Orbiter or the ISS.

Wagenknecht, J.↗

DOE OSTI2022

A workflow for segmenting soil and plant X-ray computed tomography images with deep learning in Google’s Colaboratory

X-ray micro-computed tomography (X-ray μCT) has enabled the characterization of the properties and processes that take place in plants and soils at the micron scale. Despite the widespread use of this advanced technique, major limitations in both hardware and software limit the speed and accuracy of image processing and data analysis. Recent advances in machine learning, specifically the application of convolutional neural networks to image analysis, have enabled rapid and accurate segmentation of image data. Yet, challenges remain in applying convolutional neural networks to the analysis of environmentally and agriculturally relevant images. Specifically, there is a disconnect between the computer scientists and engineers, who build these AI/ML tools, and the potential end users in agricultural research, who may be unsure of how to apply these tools in their work. Additionally, the computing resources required for training and applying deep learning models are unique, more common to computer gaming systems or graphics design work, than to traditional computational systems. To navigate these challenges, we developed a modular workflow for applying convolutional neural networks to X-ray μCT images, using low-cost resources in Google’s Colaboratory web application. Here we present the results of the workflow, illustrating how parameters can be optimized to achieve best results using example scans from walnut leaves, almond flower buds, and a soil aggregate. We expect that this framework will accelerate the adoption and use of emerging deep learning techniques within the plant and soil sciences.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2005

Landmark navigation and target characterization in a simulated Itokawa encounter

A simulated asteroid Itokawa was constructed from Ostro's latest radar model adding craters, rocks and fractal surfacing. Images were constructed from this model with known spacecraft positions and orientations, and asteroid pole and shape as 'ground truth', using available values for the Hayabusa camera parameters, and following the proposed encounter scenario.

stereophotoclinometry↗

NASA NTRS1984

The Shuttle Mission Simulator computer generated imagery

Equipment available in the primary training facility for the Space Transportation System (STS) flight crews includes the Fixed Base Simulator, the Motion Base Simulator, the Spacelab Simulator, and the Guidance and Navigation Simulator. The Shuttle Mission Simulator (SMS) consists of the Fixed Base Simulator and the Motion Base Simulator. The SMS utilizes four visual Computer Generated Image (CGI) systems. The Motion Base Simulator has a forward crew station with six-degrees of freedom motion simulation. Operation of the Spacelab Simulator is planned for the spring of 1983. The Guidance and Navigation Simulator went into operation in 1982. Aspects of orbital visual simulation are discussed, taking into account the earth scene, payload simulation, the generation and display of 1079 stars, the simulation of sun glare, and Reaction Control System jet firing plumes. Attention is also given to landing site visual simulation, and night launch and landing simulation.

Henderson, T. H.↗

NASA NTRSDate not supplied

Monocular Horizon Navigation

The Artemis program advances towards operations on the lunar surface, where precise surface localization is a driving need for safety and science. Using the observable horizon as an image landmark allows for estimating the photographer’s position. This work analyzes the application of Perspective-n-Point (PnP) algorithms to this lunar localization problem. Batch simulations using lunar topography display the accuracy and drawbacks of these methods. Monte Carlo techniques show the pipeline’s solutions as measurements provided to a navigation filter. When filtered, these solutions have position errors of 50 meters or better, which is similar to or better than the performance of other methods of surface localization.

optical navigation↗

NASA NTRS2012

Autonomous Navigation Performance During The Hartley 2 Comet Flyby

On November 4, 2010, the EPOXI spacecraft performed a 700-km flyby of the comet Hartley 2 as follow-on to the successful 2005 Deep Impact prime mission. EPOXI, an extended mission for the Deep Impact Flyby spacecraft, returned a wealth of visual and infrared data from Hartley 2, marking the fifth time that high-resolution images of a cometary nucleus have been captured by a spacecraft. The highest resolution science return, captured at closest approach to the comet nucleus, was enabled by use of an onboard autonomous navigation system called AutoNav. AutoNav estimates the comet-relative spacecraft trajectory using optical measurements from the Medium Resolution Imager (MRI) and provides this relative position information to the Attitude Determination and Control System (ADCS) for maintaining instrument pointing on the comet. For the EPOXI mission, AutoNav was tasked to enable continuous tracking of a smaller, more active Hartley 2, as compared to Tempel 1, through the full encounter while traveling at a higher velocity. To meet the mission goal of capturing the comet in all MRI science images, position knowledge accuracies of +/- 3.5 km (3-?) cross track and +/- 0.3 seconds (3-?) time of flight were required. A flight-code-in-the-loop Monte Carlo simulation assessed AutoNav's statistical performance under the Hartley 2 flyby dynamics and determined optimal configuration. The AutoNav performance at Hartley 2 was successful, capturing the comet in all of the MRI images. The maximum residual between observed and predicted comet locations was 20 MRI pixels, primarily influenced by the center of brightness offset from the center of mass in the observations and attitude knowledge errors. This paper discusses the Monte Carlo-based analysis that led to the final AutoNav configuration and a comparison of the predicted performance with the flyby performance.

flyby↗

DOE OSTI2019

Development of a Semi-autonomous Miniature Rover for Inspection of Double Shell Tank Floors - 19575

Leaks in the primary liner of double-shell tank (DST) 241-AY-102 at Hanford have prompted the need for the development of inspection tools that are able to access confined spaces around and underneath the tanks. Last year, Florida International University (FIU) has continued to improve inspection tools that were developed in the previous years, to ensure that the resultant tools are able to overcome the challenges posed by the DSTs. Experimental testing conducted last year at the full-scale sectional mock-up of the DST's refractory slots revealed some shortcomings of the miniature rover, particularly in traversing over weld seams of different heights. The weld seams are the results of welded steel plate-joints for the DST. It was advised by the site engineers that the weld seams height could range from 6.35 mm - 9.525 mm (1/4 to 3/8 inches), and with 12.7 mm (1/2 inches) width. As the rover traverses over a weld seam, the gap between the rover's magnets and tank surface increases, causing the adhesive force to drop. The rover loses its surface contact if this adhesive force drops below its weight, jeopardizing the inspection tasks. In this paper, we present the numerical studies to calculate the minimum magnetic force required for the miniature rover to traverse over weld seams with different heights and the corresponding modifications to the rover design. Initial bench scale tests were conducted using a steel bar with 5 welds of varying heights. The testing validated the results from the simulation studies and established the rover's capability in traversing weld seams. Another challenge for the miniature rover is the use of a joystick or keypad for manual control. Utilizing these controls will likely be difficult for the operators due to the tight channels underneath the tank. Having a semi-autonomous navigational capability would alleviate the complexity of the inspection tasks and allow the operator to focus on the channel inspection. The goal is to implement lane-keeping capability, akin to that of a driverless car, for the inspection tool, so that it will maintain its relative position with respect to the wall of the channels. Am image processing pipeline has been developed using both the Robot Operating System (ROS) and OpenCV to process the image stream coming from the onboard camera, for the purpose of lane identification. Additionally, a PID controller has been implemented to navigate the miniature rover along the central location of the detected lane, while allowing the operator to control the tool's forward and backward motion. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

NASA NTRSDate not supplied

Optical Deep-Space Instrument for Navigation (ODIN)

The Optical Deep-Space Instrument for Navigation (ODIN) is a proposed multiple camera, multiple field of view, optical navigation (OPNAV) instrument currently under development. ODIN aims to create a self-sufficient system which can perform imaging target acquisition, star field based attitude estimation, and position estimation using horizon-based OPNAV of known celestial bodies. ODIN will complete these tasks autonomously, thereby contributing to the advancement of OPNAV as an option for truly autonomous mission operations.

Optical Navigation↗

NASA NTRSDate not supplied

Optical Deep-Space Instrument for Navigation (ODIN)

Optical Navigation↗

NASA NTRS1979

Flight Mechanics/Estimation Theory Symposium

Onboard and real time image processing to enhance geometric correction of the data is discussed with application to autonomous navigation and attitude and orbit determination. Specific topics covered include: (1) LANDSAT landmark data; (2) star sensing and pattern recognition; (3) filtering algorithms for Global Positioning System; and (4) determining orbital elements for geostationary satellites.

Fuchs, A. J.↗

NASA NTRS1997

Navigation for the new millennium: Autonomous navigation for Deep Space 1

The autonomous optical navigation system technology for the Deep Space 1 (DS1) mission is reported on. The DS1 navigation system will be the first to use autonomous navigation in deep space. The systems tasks are to: perform interplanetary cruise orbit determination using images of distant asteroids; control and maintain the orbit of the spacecraft with an ion propulsion system and conventional thrusters, and perform late knowledge updates of target position during close flybys in order to facilitate high quality data return from asteroid MaAuliffe and comet West-Kohoutek-Ikemura. To accomplish these tasks, the following functions are required: picture planning; image processing; dynamical modeling and integration; planetary ephemeris and star catalog handling; orbit determination; data filtering and estimation; maneuver estimation, and spacecraft ephemeris updating. These systems and functions are described and preliminary performance data are presented.

Reidel, J. E.↗

NASA NTRS1996

On-Board Perception System For Planetary Aerobot Balloon Navigation

NASA's Jet Propulsion Laboratory is implementing the Planetary Aerobot Testbed to develop the technology needed to operate a robotic balloon aero-vehicle (Aerobot). This earth-based system would be the precursor for aerobots designed to explore Venus, Mars, Titan and other gaseous planetary bodies. The on-board perception system allows the aerobot to localize itself and navigate on a planet using information derived from a variety of celestial, inertial, ground-imaging, ranging, and radiometric sensors.

Planetary Aerobot Testbed robotic balloon aero-veh↗

NASA NTRS2007

Synthetic Vision Systems - Operational Considerations Simulation Experiment

Synthetic vision is a computer-generated image of the external scene topography that is generated from aircraft attitude, high-precision navigation information, and data of the terrain, obstacles, cultural features, and other required flight information. A synthetic vision system (SVS) enhances this basic functionality with real-time integrity to ensure the validity of the databases, perform obstacle detection and independent navigation accuracy verification, and provide traffic surveillance. Over the last five years, NASA and its industry partners have developed and deployed SVS technologies for commercial, business, and general aviation aircraft which have been shown to provide significant improvements in terrain awareness and reductions in the potential for Controlled-Flight-Into-Terrain incidents/accidents compared to current generation cockpit technologies. It has been hypothesized that SVS displays can greatly improve the safety and operational flexibility of flight in Instrument Meteorological Conditions (IMC) to a level comparable to clear-day Visual Meteorological Conditions (VMC), regardless of actual weather conditions or time of day. An experiment was conducted to evaluate SVS and SVS-related technologies as well as the influence of where the information is provided to the pilot (e.g., on a Head-Up or Head-Down Display) for consideration in defining landing minima based upon aircraft and airport equipage. The "operational considerations" evaluated under this effort included reduced visibility, decision altitudes, and airport equipage requirements, such as approach lighting systems, for SVS-equipped aircraft. Subjective results from the present study suggest that synthetic vision imagery on both head-up and head-down displays may offer benefits in situation awareness; workload; and approach and landing performance in the visibility levels, approach lighting systems, and decision altitudes tested.

Kramer, Lynda J.↗

NASA NTRS2008

Analysis of On-board Hazard Detection and Avoidance for Safe Lunar Landing

Landing hazard detection and avoidance technology is being pursued within NASA to improve landing safety and increase access to sites of interest on the lunar surface. The performance of a hazard detection and avoidance system depends on properties of the terrain, sensor performance, algorithm design, vehicle characteristics and the overall all guidance navigation and control architecture. This paper analyzes the size of the region that must be imaged, sensor performance parameters and the impact of trajectory angle on hazard detection performance. The analysis shows that vehicle hazard tolerance is the driving parameter for hazard detection system design.

hazard detection↗

NASA NTRS1995

Demonstration of Autonomous Orbit Determination Around Small Bodies

An algorithm is described and demonstrated with a simulation that has been developed for navigation around small bodies. This is important because of the cost and complexity of using ground control for navigating around such objects. The algorithm uses a precomputed shape model of the object and images taken with a wide field-of-view (FOV) camera.

Riedel, J.E.↗

NASA NTRS2008

Visual Target Tracking on the Mars Exploration Rovers

Visual Target Tracking (VTT) has been implemented in the new Mars Exploration Rover (MER) Flight Software (FSW) R9.2 release, which is now running on both Spirit and Opportunity rovers. Applying the normalized cross-correlation (NCC) algorithm with template image magnification and roll compensation on MER Navcam images, VTT tracks the target and enables the rover to approach the target within a few cm over a 10 m traverse. Each VTT update takes 1/2 to 1 minute on the rovers, 2-3 times faster than one Visual Odometry (Visodom) update. VTT is a key element to achieve a target approach and instrument placement over a 10-m run in a single sol in contrast to the original baseline of 3 sols. VTT has been integrated into the MER FSW so that it can operate with any combination of blind driving, Autonomous Navigation (Autonav) with hazard avoidance, and Visodom. VTT can either guide the rover towards the target or simply image the target as the rover drives by. Three recent VTT operational checkouts on Opportunity were all successful, tracking the selected target reliably within a few pixels.

target approach↗